Related papers: PAL*M: Property Attestation for Large Generative M…

Powerful large language models have facilitated the development of writing assistants that promise to significantly improve the quality and efficiency of composition and communication. However, a barrier to effective assistance is the lack…

Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation of data attribution models through techniques like empirical…

Probabilistic model checking is a widely used formal verification technique to automatically verify qualitative and quantitative properties for probabilistic models. However, capturing such systems, writing corresponding properties, and…

Generative AI models, such as GPT-4 and Stable Diffusion, have demonstrated powerful and disruptive capabilities in natural language and image tasks. However, deploying these models in decentralized environments remains challenging. Unlike…

Generative Artificial Intelligence (GenAI) has demonstrated its capabilities in the present world that reduce human effort significantly. It utilizes deep learning techniques to create original and realistic content in terms of text,…

Large language models (LLMs) have shown that generative pretraining can distill vast world knowledge into compact token representations. While LLMs encapsulate extensive world knowledge, they remain limited in modeling the behavioral…

The widespread integration of embedded systems across various industries has facilitated seamless connectivity among devices and bolstered computational capabilities. Despite their extensive applications, embedded systems encounter…

Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when fine-tuning…

A critical need has emerged for generative AI: attribution methods. That is, solutions that can identify the model originating AI-generated content. This feature, generally relevant in multimodal applications, is especially sensitive in…

In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective…

Accurately predicting task performance at runtime in a cluster is advantageous for a resource management system to determine whether a task should be migrated due to performance degradation caused by interference. This is beneficial for…

This work presents a generative modeling approach based on successive subspace learning (SSL). Unlike most generative models in the literature, our method does not utilize neural networks to analyze the underlying source distribution and…

The growing complexity of modern system-on-chip (SoC) and IP designs is making security assurance difficult day by day. One of the fundamental steps in the pre-silicon security verification of a hardware design is the identification of…

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM…

Large language models (LLMs) deliver impressive performance but incur prohibitive memory and compute costs at deployment. Model pruning is an effective way to reduce these overheads, yet existing approaches face challenges: unstructured…

Previous works have demonstrated the importance of considering different modalities on molecules, each of which provide a varied granularity of information for downstream property prediction tasks. Our method combines variants of the recent…

Vision-Language-Action (VLA) models have become a prominent paradigm for embodied intelligence, yet further performance improvements typically rely on scaling up training data and model size -- an approach that is prohibitively expensive…

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key principle underlying the design of PowerInfer is exploiting the high…

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

One of the motivations for property testing of boolean functions is the idea that testing can serve as a preprocessing step before learning. However, in most machine learning applications, it is not possible to request for labels of…